dealign.ai PRO

dealignai's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in dealignai/GLM-5.3-UNCENSORED-FP8 about 2 hours ago

V2 still degenerates into word salad on real long-context agent workloads

1

#2 opened about 15 hours ago by

leonice2

New activity in dealignai/Qwen3.8-Flash-Next-UNCENSORED-FP8 about 5 hours ago

Reasoning-trace length: abliterated vs. base Qwen3.8-Flash-Next on GPQA Diamond

8

#2 opened 4 days ago by

Soomin33

New activity in dealignai/Qwen3.8-Flash-Next-CYBERSECURITY-NVFP4 1 day ago

Reasoning improvements?

1

#1 opened 1 day ago by

dealignai

New activity in dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 5 days ago

Token output random corruption, ModelOpt artifact?

1

#2 opened 6 days ago by

atrix

New activity in dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 7 days ago

Vision not working

3

#1 opened 7 days ago by

GulfCoastAI

New activity in dealignai/GLM-5.3-Flash-UNCENSORED-FP8 7 days ago

GGUF?

5

#1 opened 9 days ago by

kabachuha

New activity in dealignai/Qwen3.8-27B-UNCENSORED-GGUF 16 days ago

ty dealignai <3

👍 1

4

#2 opened 16 days ago by

0xHgageface

New activity in dealignai/Qwen3.8-27B-UNCENSORED-GGUF 20 days ago

Feature request — CRACK + Claude Opus 4.7-style reasoning distillation

1

#1 opened 20 days ago by

imedox

New activity in dealignai/DeepSeek-V4-Flash-JANG-CRACK 24 days ago

Unsupported safetensors format: null

2

#1 opened 3 months ago by

Mod-1

New activity in stamsam/Gemma-4-21B-REAP-JANG3M-MLX 3 months ago

Interesting work!

1

#1 opened 3 months ago by

dealignai

New activity in dealignai/Gemma-4-31B-JANG_4M-CRACK 3 months ago

Fix loading in LM Studio / mlx-llm: quant map keys + vision weights

4

#25 opened 4 months ago by

IsaacLiu

New activity in dealignai/Gemma-4-26B-A4B-JANG_4M-CRACK 3 months ago

Gemma 4 26B (A4B) - Garbage output (korean/chinese) on MLX 0.31.2 while 31B works fine

3

#2 opened 5 months ago by

Z3NN001

New activity in OsaurusAI/MiniMax-M2.7-JANGTQ_K 4 months ago

Add MMLU-200 (93.5%), speed/memory benchmarks, fix variants table sizes (47→56 GB), expand topic tags

#1 opened 4 months ago by

dealignai

New activity in dealignai/Gemma-4-31B-JANG_4M-CRACK 5 months ago

gemma4-crack

#8 opened 5 months ago by

Adam666Eves

Bug

3

#3 opened 5 months ago by

Zayaan

New activity in dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK 5 months ago

non-mac

1

#1 opened 5 months ago by

pirola

New activity in dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK 5 months ago

lm-studio

2

#2 opened 5 months ago by

hady20100

turboquant module?

1

#1 opened 5 months ago by

abbuu

New activity in dealignai/Gemma-4-31B-JANG_4M-CRACK 5 months ago

Can you please release GGUF versions ?

7

#1 opened 5 months ago by

PaPaai99

Refusal rate very high on questions beyond cybersecurity

8

#4 opened 5 months ago by

Zayaan